Scientific computing and parallel computing C++23/C++26
Guillaume Piolat
first.last at gmail.com
Sat Jan 15 10:35:29 UTC 2022
On Saturday, 15 January 2022 at 09:03:11 UTC, Nicholas Wilson
wrote:
>
> from what I understand unified memory allows the GPU to access
> the host RAM with the same pointer. This reduces the total
> memory consumed by the program, but to get to the GPU the data
> must still cross the PCI-e.
Exactly. I remember that in 2013 "Unified Memory Access" on
NVIDIA was underwhelming, performing worse than pinned transfer +
GPU memory access.
More information about the Digitalmars-d
mailing list